def findSol(self, timewindow):
pyevolve.logEnable()
genome = G1DList.G1DList(4)
# range is constrained by the solutions found by MR
genome.setParams(rangemin=-12.0, rangemax=2.0)
# Change the initializator to Real Values
genome.initializator.set(Initializators.G1DListInitializatorReal)
# Change the mutator to Gaussian
genome.mutator.set(Mutators.G1DListMutatorRealGaussian)
# The evaluator function (objective function)
genome.evaluator.set(self.eval_func(self.features))
genome.crossover.set(Crossovers.G1DListCrossoverTwoPoint)
# Genetic Algorithm Instance
ga = GSimpleGA.GSimpleGA(genome)
# Set the Roulette Wheel selector method, the number of generations and
# the termination criteria
ga.selector.set(Selectors.GRouletteWheel)
# set default parameters for the engine
ga.setGenerations(100)
#ga.setPopulationSize(80)
#ga.setMutationRate(0.2)
#ga.setCrossoverRate(0.8)
ga.setMinimax(Consts.minimaxType["minimize"])
ga.setElitism(True)
ga.terminationCriteria.set(GSimpleGA.ConvergenceCriteria)
# Sets the DB Adapter, the resetDB flag will make the Adapter recreate
# the database and erase all data every run, you should use this flag
# just in the first time, after the pyevolve.db was created, you can
# omit it.
#sqlite_adapter = DBAdapters.DBSQLite(identify="ex1", resetDB=True)
dbPath = createPath('pyevolve.db')
sqlite_adapter = DBAdapters.DBSQLite(dbname=dbPath,
identify="timewindow" +
str(timewindow),
resetIdentify=True,
resetDB=False)
ga.setDBAdapter(sqlite_adapter)
# Do the evolution, with stats dump frequency of 20 generations
ga.evolve(freq_stats=20)
# Best individual
best = ga.bestIndividual()
stats = {
'constant': best[0],
'EMA': best[1],
'RSI': best[2],
'MACD': best[3]
}
return stats
def findSol(self, timewindow):
pyevolve.logEnable()
genome = G1DList.G1DList(4)
# range is constrained by the solutions found by MR
genome.setParams(rangemin=-12.0, rangemax=2.0)
# Change the initializator to Real Values
genome.initializator.set(Initializators.G1DListInitializatorReal)
# Change the mutator to Gaussian
genome.mutator.set(Mutators.G1DListMutatorRealGaussian)
# The evaluator function (objective function)
genome.evaluator.set(self.eval_func(self.features))
genome.crossover.set(Crossovers.G1DListCrossoverTwoPoint)
# Genetic Algorithm Instance
ga = GSimpleGA.GSimpleGA(genome)
# Set the Roulette Wheel selector method, the number of generations and
# the termination criteria
ga.selector.set(Selectors.GRouletteWheel)
# set default parameters for the engine
ga.setGenerations(100)
#ga.setPopulationSize(80)
#ga.setMutationRate(0.2)
#ga.setCrossoverRate(0.8)
ga.setMinimax(Consts.minimaxType["minimize"])
ga.setElitism(True)
ga.terminationCriteria.set(GSimpleGA.ConvergenceCriteria)
# Sets the DB Adapter, the resetDB flag will make the Adapter recreate
# the database and erase all data every run, you should use this flag
# just in the first time, after the pyevolve.db was created, you can
# omit it.
#sqlite_adapter = DBAdapters.DBSQLite(identify="ex1", resetDB=True)
dbPath = createPath('pyevolve.db')
sqlite_adapter = DBAdapters.DBSQLite(dbname=dbPath, identify="timewindow" + str(timewindow), resetIdentify=True, resetDB=False)
ga.setDBAdapter(sqlite_adapter)
# Do the evolution, with stats dump frequency of 20 generations
ga.evolve(freq_stats=20)
# Best individual
best = ga.bestIndividual()
stats = {'constant': best[0],
'EMA': best[1],
'RSI': best[2],
'MACD': best[3]
}
return stats
def loadFile(filename, alpha):
f = csv.reader(open(filename))
w = csv.writer(open('hTests.csv', 'w'))
count = 0
w.writerow(['t', 'mr-EMA z', 'GA-MR z', 'criticalZ'])
for line in f:
if count > 0:
t,formula,e1R2,emaR2,mrR2,e1AIC, emaAIC,mrAIC,e2R2, e2AIC = line
path = createPath('Timewindow Features', 'timewindowFeatures' + str(t) + '.csv')
n = file_len(path)
z1 = ft.fisherTransformation(math.sqrt(float(mrR2)), math.sqrt(float(emaR2)), n, n)
z1, criticalZ, hTest = ft.normHTest(z1, alpha)
z2 = ft.fisherTransformation(math.sqrt(float(e1R2)), math.sqrt(float(mrR2)), n, n)
z2, criticalZ, hTest = ft.normHTest(z2, alpha)
w.writerow([t, z1, z2, criticalZ])
count += 1
def findSol(self, windowSize):
y = np.array(self.prices)
x = np.vstack([self.ema, self.rsi, self.macd]).T
mymodel = ols.ols(y, x, 'price', ['EMA', 'RSI', 'MACD'])
labels = ['constant', 'EMA', 'RSI', 'MACD']
equation = "price(t+1) = "
stats = {}
for i in range(len(mymodel.b)):
l = labels[i]
c = mymodel.b[i]
stats[l] = c
if l == 'constant':
equation += str(c) + " + "
else:
equation += str(c) + "*" + l + "(t) + "
equation = equation[:-2]
return stats
stocks = ['C', 'FDX', 'KO', 'MSFT', 'SBUX', 'NFLX', 'LUV']
for s in stocks:
path = createPath(s + '/' + s + 'mrValidation.csv')
featuresPath = createPath(s + '/')
cv.crossValidationFeatures(featuresPath, path, MRFeatures())
#ga.setMutationRate(0.2)
#ga.setCrossoverRate(0.8)
ga.setMinimax(Consts.minimaxType["minimize"])
ga.setElitism(True)
ga.terminationCriteria.set(GSimpleGA.ConvergenceCriteria)
# Sets the DB Adapter, the resetDB flag will make the Adapter recreate
# the database and erase all data every run, you should use this flag
# just in the first time, after the pyevolve.db was created, you can
# omit it.
#sqlite_adapter = DBAdapters.DBSQLite(identify="ex1", resetDB=True)
dbPath = createPath('pyevolve.db')
sqlite_adapter = DBAdapters.DBSQLite(dbname=dbPath, identify="timewindow" + str(timewindow), resetIdentify=True, resetDB=False)
ga.setDBAdapter(sqlite_adapter)
# Do the evolution, with stats dump frequency of 20 generations
ga.evolve(freq_stats=20)
# Best individual
best = ga.bestIndividual()
stats = {'constant': best[0],
'EMA': best[1],
'RSI': best[2],
'MACD': best[3]
}
return stats
filename = createPath('gaValidation.csv')
timeseries = loadStock('KO')
cv.crossValidationFeatures(filename, GAForecaster())
prices, ema, rsi, macd = self.tf.getTimewindow(windowSize)
y = np.array(prices)
x = np.vstack([ema, rsi, macd]).T
mymodel = ols.ols(y,x,'price',['EMA','RSI','MACD'])
labels = ['constant', 'EMA','RSI','MACD']
equation = "price(t+1) = "
stats = {}
for i in range(len(mymodel.b)):
l = labels[i]
c = mymodel.b[i]
stats[l] = c
if l == 'constant':
equation += str(c) + " + "
else:
equation += str(c) + "*" + l + "(t) + "
equation = equation[:-2]
return stats
stocks = ['NFLX', 'LUV']
for s in stocks:
timeseries = loadStock(s + '/' + s)
path = createPath(s + '/' + s + 'mrValidation.csv')
featuresPath = createPath(s + '/')
cv.crossValidationFeatures(featuresPath, path, timeseries, MultipleRegression())
def findSol(self, windowSize):
prices, ema, rsi, macd = self.tf.getTimewindow(windowSize)
y = np.array(prices)
x = np.vstack([ema]).T
mymodel = ols.ols(y,x,'price',['EMA'])
labels = ['constant', 'EMA']
equation = "price(t+1) = "
stats = {}
for i in range(len(mymodel.b)):
l = labels[i]
c = mymodel.b[i]
stats[l] = c
if l == 'constant':
equation += str(c) + " + "
else:
equation += str(c) + "*" + l + "(t) + "
equation = equation[:-2]
return stats
stocks = ['NFLX', 'LUV']
for s in stocks:
timeseries = loadStock(s + '/' + s)
path = createPath(s + '/' + s + 'emaValidation.csv')
cv.simpleCrossValidation(path, timeseries, SimpleRegression())
prices, ema, rsi, macd = self.tf.getTimewindow(windowSize)
y = np.array(prices)
x = np.vstack([ema]).T
mymodel = ols.ols(y, x, 'price', ['EMA'])
labels = ['constant', 'EMA']
equation = "price(t+1) = "
stats = {}
for i in range(len(mymodel.b)):
l = labels[i]
c = mymodel.b[i]
stats[l] = c
if l == 'constant':
equation += str(c) + " + "
else:
equation += str(c) + "*" + l + "(t) + "
equation = equation[:-2]
return stats
stocks = ['NFLX', 'LUV']
for s in stocks:
timeseries = loadStock(s + '/' + s)
path = createPath(s + '/' + s + 'emaValidation.csv')
cv.simpleCrossValidation(path, timeseries, SimpleRegression())
with open(fname) as f:
for i, l in enumerate(f):
pass
return i + 1
def loadFile(filename, alpha):
f = csv.reader(open(filename))
w = csv.writer(open('hTests.csv', 'w'))
count = 0
w.writerow(['t', 'mr-EMA z', 'GA-MR z', 'criticalZ'])
for line in f:
if count > 0:
t,formula,e1R2,emaR2,mrR2,e1AIC, emaAIC,mrAIC,e2R2, e2AIC = line
path = createPath('Timewindow Features', 'timewindowFeatures' + str(t) + '.csv')
n = file_len(path)
z1 = ft.fisherTransformation(math.sqrt(float(mrR2)), math.sqrt(float(emaR2)), n, n)
z1, criticalZ, hTest = ft.normHTest(z1, alpha)
z2 = ft.fisherTransformation(math.sqrt(float(e1R2)), math.sqrt(float(mrR2)), n, n)
z2, criticalZ, hTest = ft.normHTest(z2, alpha)
w.writerow([t, z1, z2, criticalZ])
count += 1
path = createPath('modelsComparison.csv')
loadFile(path, 0.05)
# Sets the DB Adapter, the resetDB flag will make the Adapter recreate
# the database and erase all data every run, you should use this flag
# just in the first time, after the pyevolve.db was created, you can
# omit it.
#sqlite_adapter = DBAdapters.DBSQLite(identify="ex1", resetDB=True)
dbPath = createPath('pyevolve.db')
sqlite_adapter = DBAdapters.DBSQLite(dbname=dbPath,
identify="timewindow" +
str(timewindow),
resetIdentify=True,
resetDB=False)
ga.setDBAdapter(sqlite_adapter)
# Do the evolution, with stats dump frequency of 20 generations
ga.evolve(freq_stats=20)
# Best individual
best = ga.bestIndividual()
stats = {
'constant': best[0],
'EMA': best[1],
'RSI': best[2],
'MACD': best[3]
}
return stats
filename = createPath('gaValidation.csv')
timeseries = loadStock('KO')
cv.crossValidationFeatures(filename, GAForecaster())
